mlsanityData to 7 Oct 2026

Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures

arXiv 2209.11159 ↗First posted 22 Sep 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Labeling images for visual segmentation is a time-consuming task which can be costly, particularly in application domains where labels have to be provided by specialized expert annotators, such as civil engineering. In this paper, we propose to use attribution methods to harness the valuable interactions between expert annotators and the data to be annotated in the case of defect segmentation for visual inspection of civil infrastructures. Concretely, a classifier is trained to detect defects and coupled with an attribution-based method and adversarial climbing to generate and refine segmentation masks corresponding to the classification outputs. These are used within an assisted labeling framework where the annotators can interact with them as proposal segmentation masks by deciding to accept, reject or modify them, and interactions are logged as weak labels to further refine the classifier. Applied on a real-world dataset resulting from the automated visual inspection of bridges, our proposed method is able to save more than 50% of annotators' time when compared to manual annotation of defects.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 22 Sep 2022.

Builds on

23 of 31 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  6. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
  7. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  8. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  9. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 168
  10. 2018Adversarial Complementary Learning for Weakly Supervised Object Localizationcited by 166
  11. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
  12. 2020Weakly-Supervised Semantic Segmentation via Sub-category Explorationcited by 145
11 more
  1. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  2. 2017Deep Extreme Cut: From Extreme Points to Object Segmentationcited by 127
  3. 2018Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++cited by 119
  4. 2019Large-scale interactive object segmentation with human annotatorscited by 109
  5. 2018Self-Erasing Network for Integral Object Attentioncited by 95
  6. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  7. 2020NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Imagescited by 46
  8. 2022Bridging the Gap between Classification and Localization for Weakly Supervised Object Localizationcited by 25
  9. 2020In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localizationcited by 16
  10. 2022Poly-CAM: High resolution class activation map for convolutional neural networkscited by 10
  11. 2019HR-CAM: Precise Localization of Pathology Using Multi-level Learning in CNNscited by 4

Built on by

Not cited yet.